blogReinforcement Learning
Bellman Optimality as a Planning Lens
A compact note on why the Bellman equation is more than a recurrence: it is a way to organize decisions under uncertainty.
Knowledge base
Search
Search the local content index across titles, descriptions, tags, categories, and full text.
8 results
blogWorld Model
What I Mean by a World Model
A working definition for connecting perception, temporal prediction, and action in embodied learning systems.
notesDSP
IIR Filters and Quantization Error
A study note on how finite precision changes the behavior of recursive digital filters.
notesExperiment Logs
Experiment Log: Conditioning a Video Diffusion Model
An early record of how affordance conditioning changes temporal consistency in generated driving scenes.
papersWorld Model
Learning Latent Dynamics for Long-Horizon Video Prediction
papersAutonomous Driving
Planning-oriented Autonomous Driving
projectsAutonomous Driving
Affordance-conditioned Accident Video Generation
A research project exploring controllable video generation for rare traffic interactions and safety analysis.
projectsResearch Practice
Research Notebook
The evolving system behind experiments, paper notes, and research questions in this knowledge base.